[00:01] Over the past few years, large language models have become very good at understanding and generating text. But the next question is, can these models actually do things?
[00:14] This is where agents come in. An agent is a system that can take in a goal, reason about needed steps, use tools, and adapt based on what happens along the way.
[00:26] For example, instead of answering a question only based on knowledge, an agent might search for information, write code, call an API, analyze the result, and decide what to do
[00:38] next. And this is exciting because it moves AI systems from being mostly conversational to being more action-oriented, but it also raises important challenges. First, how do we make agents reliable?
[00:51] How do we evaluate them? and how do we make sure they can plan without going off track? In CME 295, Transformers and Large Language Models, we cover these ideas by grounding them with the latest technical advances.
[01:05] Shervin and I hope to see you there!